NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PZ13QPMTZHMRNQW6659QQ
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.6s
Cost:
$0.004819
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
86.79%
Dialogue to Total Word Ratio
(details)
92.7508%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
"Bill, we go in, we take the presents, we leave. Simple." "Question." "You haven't heard the plan yet." "My question is about the plan I'm imagining." "Fine. What?" "Are we going in as clowns?" "Why would we go in as clowns?" "It's a kids' party, Molly. Clowns blend in." "Clowns don't blend in anywhere. That's the whole point of clowns." "Counterpoint: I already rented the costume." "You rented a clown suit for a heist?" "Forty quid. Non-refundable." "Fine. Wear the stupid clown suit." "Second question. Are we stealing the presents before or after the magician?" "Why does that matter?" "During the magician, everyone watches him. Perfect cover." "That's... actually not your worst idea." "I've been reading heist books." "You read the back of my book once, in the bath." "And I retained a lot, Molly. What about the birthday girl?" "What about her?" "Do we steal her present too? Feels dark." "We're stealing presents from children, Bill. It's all dark." "Noted. Final question." "Make it fast." "Can we have cake first?" "We're not having cake." "There's a bouncy castle, isn't there?" "We are not going in the bouncy castle." "Then what am I even doing this for, Molly?" Bill adjusted his giant bow tie and sighed.
created_at
"2026-09-23T18:03:07.27Z"
9/23/2026, 6:03:07 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
651
moderation_latency
(null)
generation_time
14586
tokens_prompt
75
tokens_completion
885
native_tokens_prompt
65
native_tokens_completion
795
native_tokens_completion_images
(null)
native_tokens_reasoning
556
native_tokens_cached
65
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.00481875
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186587-q67MjmuPsyESS0m0FLLw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186587-sZd0HSgaJlW9xKnEgOI4"
upstream_id
"800b8074643448d08fe5063024a60603"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"800b8074643448d08fe5063024a60603"
is_byok
false
latency
651
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00481875
cache_discount
0.00014625
upstream_inference_cost
0
provider_name
"AionLabs"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
86.79%
Dialogue to Total Word Ratio
Ratio: 96.14%, Deviation: 6.14%
neededClean
false
wordsTotal
207
wordsDialogue
199
92.7508%